Blog

Mostly technical, occasionally not.

Notes on the products I'm building, migrations, AI systems — and every so often, whatever else is on my mind.

How I decide if a product idea is worth building

As a product strategist, the job before the build is killing the ideas that don't survive contact with a business model.

Most of the work in a real AI product is retrieval, evaluation, and cost control — not the model call itself.

Why I mapped every indexed URL before writing a single line of the new frontend.

Strategy, engineering, AI, and brand aren't separate jobs to me — they're one feedback loop.